pith. sign in

arxiv: 2606.25619 · v1 · pith:QS57ZFTOnew · submitted 2026-06-24 · 💻 cs.CV

ScaleHP: Estimating Hand Pose in Metric Space

Ruitao Jing , Xingyu Chen , Hongyang Li , Qing Jiang , Yukai Shi , Lei Zhang This is my paper

Pith reviewed 2026-06-25 21:03 UTC · model grok-4.3

classification 💻 cs.CV
keywords hand pose estimationmetric spaceanthropometric priorsscale tokentransformer decoderleast-squares optimization3D hand tracking
0
0 comments X

The pith

Hand bone proportions encode absolute metric scale for single-image 3D pose estimation.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes that intrinsic proportional relationships among hand bones provide stable priors correlating with overall hand size, enabling estimation of poses in absolute metric camera coordinates. This is important because existing methods typically output only root-relative poses, which lack the absolute scale needed for applications like robotics and immersive interaction. ScaleHP implements this by using a transformer-based decoder with a scale token to integrate multi-scale features and then applies perspective-constrained least-squares to recover metric positions. The method achieves state-of-the-art results on standard benchmarks without relying on external depth data or calibration.

Core claim

By observing that proportional relationships among human hand bones encode stable anthropometric priors that implicitly correlate with the overall metric size, ScaleHP recovers hand poses directly in metric space using an end-to-end framework with a scale token in a transformer decoder and perspective-constrained least-squares optimization, achieving 35.8 CS-MPJPE on FreiHand and 4.6/5.9 PA-MPJPE on DexYCB/HO3Dv3.

What carries the argument

The scale token in the transformer-based decoder that fuses multi-scale morphological and appearance features to enable metric coordinate recovery via perspective-constrained least-squares.

If this is right

  • Internal biological constraints reduce both relative geometry and absolute metric errors in hand pose estimates.
  • Metric-space hand tracking becomes possible without fragile extrinsic depth modules or person-specific calibration.
  • State-of-the-art performance is achieved on FreiHand, DexYCB, and HO3Dv3 benchmarks.
  • The approach offers a robust solution for generalized real-world hand tracking in human-computer interaction and robotics.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar proportion-based priors could apply to metric estimation for other articulated structures where stable ratios exist.
  • Accuracy would drop if bone proportions vary substantially across populations not represented in training data.
  • The least-squares step could combine with additional geometric cues such as known camera intrinsics for further gains.

Load-bearing premise

Hand bone length proportions remain stable across individuals and implicitly encode absolute metric scale without person-specific calibration.

What would settle it

Empirical measurement of hand bone proportions across a diverse population showing variations large enough to cause substantial metric pose estimation errors on the reported benchmarks.

Figures

Figures reproduced from arXiv: 2606.25619 by Hongyang Li, Lei Zhang, Qing Jiang, Ruitao Jing, Xingyu Chen, Yukai Shi.

Figure 1
Figure 1. Figure 1: We present ScaleHP, an one-stage framework for hand pose estimation in Metric Space. This method is the first to explicitly predict the global scale of the hand, enabling accurate recovery of the hand pose in the true metric space, which previous approaches failed to achieve. the bridge between human intent and robotic execution. For a robot to perform dexterous manipulation—such as picking up a fragile to… view at source ↗
Figure 2
Figure 2. Figure 2: Overview of ScaleHP Framework. The model first extracts global hand features and detection cues from a frozen detector. These features are fed into the Metric 2D–3D Decoder, where the scale token interacts with queries representing 2D and 3D keypoints as well as image features. Subsequently, a training-free analytic module solves for the global translation, allowing the framework to estimate hand poses wit… view at source ↗
Figure 3
Figure 3. Figure 3: Qualitative Comparison on the FreiHand evaluation set. [PITH_FULL_IMAGE:figures/full_fig_p013_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative Results of ScaleHP on In-the-Wild Images. [PITH_FULL_IMAGE:figures/full_fig_p014_4.png] view at source ↗
read the original abstract

Accurate metric-space hand pose estimation (HPE) is essential for immersive human-computer interaction and robotics. However, most existing methods predict poses in a root-relative coordinate system and cannot estimate the hand in absolute metric scale. In this work, we observe that the intrinsic proportional relationships among human hand bones encode stable anthropometric priors that implicitly correlate with the overall metric size of the hand. Leveraging this insight, we present ScaleHP, an end-to-end one-stage hand pose estimation framework that bypasses fragile extrinsic depth modules to recover the hand in metric space. ScaleHP employs a transformer-based decoder with a novel scale token to fuse multi-scale morphological and appearance features. By solving for metric coordinates through a perspective-constrained least-squares approach, we achieve high-precision pose estimation in the camera coordinate system. ScaleHP delivers state-of-the-art performance, including 35.8 CS-MPJPE on FreiHand and 4.6/5.9 PA-MPJPE on DexYCB and HO3Dv3. These results demonstrate that internal biological constraints significantly reduce relative geometry and absolute metric errors, offering a robust solution for generalized, real-world hand tracking.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 1 minor

Summary. The paper claims that intrinsic proportional relationships among human hand bones encode stable anthropometric priors correlating with overall metric hand size; ScaleHP uses a transformer decoder with a novel scale token to fuse features and a perspective-constrained least-squares solver to recover absolute metric pose in camera coordinates, achieving SOTA results of 35.8 CS-MPJPE on FreiHand and 4.6/5.9 PA-MPJPE on DexYCB/HO3Dv3 without external depth or calibration.

Significance. If the bone-proportion-to-metric-scale correlation holds with sufficient tightness, the work would be significant for enabling calibration-free metric HPE in HCI and robotics. The reported empirical results on three standard datasets are competitive and the one-stage design is a practical strength; however, the significance is limited by the absence of explicit quantification of the prior's correlation strength or generalization tests.

major comments (3)
  1. [Abstract] Abstract: the claim that bone length proportions 'implicitly correlate with the overall metric size' is load-bearing, yet ratios are scale-invariant by construction; no quantitative correlation analysis, variance statistics, or ablation across demographics/ages/ethnicities is supplied to show that the statistical association is tight enough to determine absolute scale independently of the training distribution.
  2. [Method (perspective-constrained least-squares)] Method description of the perspective-constrained least-squares solver: the solve is presented at high level with no derivation, objective function, or error analysis; it is therefore impossible to verify whether the metric output is independent of the morphological features already used to define the scale token prior or whether it reduces to a data-driven fit.
  3. [Results] Results section: the reported CS-MPJPE and PA-MPJPE numbers are given without an ablation isolating the contribution of the bone-proportion prior versus the transformer backbone or the least-squares step, leaving the central claim that 'internal biological constraints significantly reduce ... absolute metric errors' unsupported by controlled evidence.
minor comments (1)
  1. Notation for the scale token and the least-squares variables is introduced without an explicit equation or table summarizing symbols.

Simulated Author's Rebuttal

3 responses · 1 unresolved

We thank the referee for the constructive comments, which help strengthen the presentation of our work. We address each major point below and will incorporate the suggested clarifications and analyses in the revised manuscript.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim that bone length proportions 'implicitly correlate with the overall metric size' is load-bearing, yet ratios are scale-invariant by construction; no quantitative correlation analysis, variance statistics, or ablation across demographics/ages/ethnicities is supplied to show that the statistical association is tight enough to determine absolute scale independently of the training distribution.

    Authors: We agree the claim requires quantitative backing. In revision we will add correlation analysis on the training sets (Pearson coefficients and variance between bone ratios and metric hand size) plus explicit discussion of the assumption's validity within the adult-centric distributions of FreiHand, DexYCB and HO3Dv3. We cannot supply cross-demographic ablations without new data. revision: partial

  2. Referee: [Method (perspective-constrained least-squares)] Method description of the perspective-constrained least-squares solver: the solve is presented at high level with no derivation, objective function, or error analysis; it is therefore impossible to verify whether the metric output is independent of the morphological features already used to define the scale token prior or whether it reduces to a data-driven fit.

    Authors: We will expand the method section with the full derivation, objective function (reprojection error minimized subject to the scale-token prior and perspective constraints), and error analysis demonstrating that the geometric solve recovers metric scale independently of the learned morphological features while using them only for initialization. revision: yes

  3. Referee: [Results] Results section: the reported CS-MPJPE and PA-MPJPE numbers are given without an ablation isolating the contribution of the bone-proportion prior versus the transformer backbone or the least-squares step, leaving the central claim that 'internal biological constraints significantly reduce ... absolute metric errors' unsupported by controlled evidence.

    Authors: We will add controlled ablations comparing (i) transformer backbone alone, (ii) backbone plus scale token without the least-squares solver, and (iii) the full model, thereby quantifying the prior's isolated contribution to absolute metric accuracy. revision: yes

standing simulated objections not resolved
  • Ablation or quantitative analysis across demographics, ages, and ethnicities, as this requires new annotated datasets outside the scope of the current benchmarks.

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper's central claim rests on an empirical observation about anthropometric correlations in hand bone proportions, implemented via a learned transformer decoder with scale token and a perspective-constrained least-squares solver. No load-bearing step reduces a prediction to its inputs by construction, no self-citation chain justifies uniqueness, and no ansatz or renaming is smuggled in. The metric estimation is data-driven and externally validated on FreiHand, DexYCB, and HO3Dv3, making the derivation self-contained against benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Abstract-only; no explicit free parameters, axioms, or invented entities can be extracted beyond the stated anthropometric prior.

axioms (1)
  • domain assumption Hand bone length proportions are stable across individuals and correlate with absolute hand size
    Core observation invoked to bypass external depth modules

pith-pipeline@v0.9.1-grok · 5739 in / 1098 out tokens · 19263 ms · 2026-06-25T21:03:21.685705+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

77 extracted references · 6 canonical work pages

  1. [1]

    In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019

    Baek, S., Kim, K.I., Kim, T.: Pushing the envelope for rgb-based dense 3d hand pose estimation via neural rendering. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019. pp. 1067–1076. Computer Vision Foundation / IEEE (2019).https://doi.org/ 10.1109/CVPR.2019.001163

    work page doi:10.1109/cvpr.2019.001163 2019

  2. [2]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Bhat, S.F., Alhashim, I., Wonka, P.: Adabins: Depth estimation using adaptive bins. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 4009–4018 (2021) 5

    2021

  3. [3]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Boukhayma, A., Bem, R.d., Torr, P.H.: 3d hand shape and pose from images in the wild. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 10843–10852 (2019) 2

    2019

  4. [4]

    In: European conference on computer vision

    Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End- to-end object detection with transformers. In: European conference on computer vision. pp. 213–229. Springer (2020) 4

    2020

  5. [5]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Chao,Y.W.,Yang,W.,Xiang, Y.,Molchanov,P.,Handa,A., Tremblay, J.,Narang, Y.S., Van Wyk, K., Iqbal, U., Birchfield, S., et al.: Dexycb: A benchmark for capturing hand grasping of objects. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 9044–9053 (2021) 10, 22

    2021

  6. [6]

    A ConvNet for the 2020s

    Chen, X., Liu, Y., Dong, Y., Zhang, X., Ma, C., Xiong, Y., Zhang, Y., Guo, X.: Mobrecon: Mobile-friendly hand mesh reconstruction from monocular image. In: IEEE/CVFConferenceonComputerVisionandPatternRecognition,CVPR2022, New Orleans, LA, USA, June 18-24, 2022. pp. 20512–20522. IEEE (2022).https: //doi.org/10.1109/CVPR52688.2022.019894, 6, 12 ScaleHP 17

    work page doi:10.1109/cvpr52688.2022.019894 2022

  7. [7]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Chen, X., Liu, Y., Ma, C., Chang, J., Wang, H., Chen, T., Guo, X., Wan, P., Zheng, W.: Camera-space hand mesh recovery via semantic aggregation and adaptive 2d- 1d registration. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 13274–13283 (2021) 4, 6, 12, 22

    2021

  8. [8]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Chen, X., Song, Z., Jiang, X., Hu, Y., Yu, J., Zhang, L.: Handos: 3d hand re- construction in one stage. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 17304–17314 (2025) 6, 10, 12

    2025

  9. [9]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Chen, Y., Tu, Z., Kang, D., Bao, L., Zhang, Y., Zhe, X., Chen, R., Yuan, J.: Model-based 3d hand reconstruction via self-supervised learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 10451–10460 (2021) 3

    2021

  10. [10]

    2021 IEEE/CVF ConferenceonComputerVisionandPatternRecognition(CVPR)pp.10446–10455 (2021) 12

    Chen, Y., Tu, Z., Kang, D., Bao, L., Zhang, Y., Zhe, X., Chen, R., Yuan, J.: Model-based 3d hand reconstruction via self-supervised learning. 2021 IEEE/CVF ConferenceonComputerVisionandPatternRecognition(CVPR)pp.10446–10455 (2021) 12

    2021

  11. [11]

    In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J

    Choi, H., Moon, G., Lee, K.M.: Pose2mesh: Graph convolutional network for 3d human pose and mesh recovery from a 2d human pose. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J. (eds.) Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part VII. Lecture Notes in Computer Science, vol. 12352, pp. 769–787. ...

    work page doi:10.1007/978-3-030-58571-6_45 2020

  12. [12]

    In: Glober- sons, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J.M., Zhang, C

    Dong, H., Chharia, A., Gou, W., Carrasco, F.V., la Torre, F.D.: Hamba: Single- view 3d hand reconstruction with graph-guided bi-scanning mamba. In: Glober- sons, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J.M., Zhang, C. (eds.) Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems...

    2024

  13. [13]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Ge, L., Ren, Z., Li, Y., Xue, Z., Wang, Y., Cai, J., Yuan, J.: 3d hand shape and pose estimation from a single rgb image. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 10833–10842 (2019) 4, 6

    2019

  14. [14]

    In: First conference on language modeling (2024) 4

    Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. In: First conference on language modeling (2024) 4

    2024

  15. [15]

    In: Proceedings of the IEEE/CVF Inter- national Conference on Computer Vision

    Guizilini, V., Vasiljevic, I., Chen, D., Ambrus,, R., Gaidon, A.: Towards zero-shot scale-aware monocular depth estimation. In: Proceedings of the IEEE/CVF Inter- national Conference on Computer Vision. pp. 9233–9243 (2023) 5

    2023

  16. [16]

    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp

    Hampali, S., Rad, M., Oberweger, M., Lepetit, V.: Honnotate: A method for 3d annotation of hand and object poses. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 3193–3203 (2019) 10, 22

    2020

  17. [17]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Hasson, Y., Tekin, B., Bogo, F., Laptev, I., Pollefeys, M., Schmid, C.: Leveraging photometric consistency over time for sparsely supervised hand-object reconstruc- tion. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 571–580 (2020) 2, 4

    2020

  18. [18]

    In: Proceed- ings of the IEEE/CVF conference on computer vision and pattern recognition

    Hasson, Y., Varol, G., Tzionas, D., Kalevatykh, I., Black, M.J., Laptev, I., Schmid, C.: Learning joint reconstruction of hands and manipulated objects. In: Proceed- ings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 11807–11816 (2019) 3, 12

    2019

  19. [19]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Huang, L., Lin, C.C., Lin, K., Liang, L., Wang, L., Yuan, J., Liu, Z.: Neural voting field for camera-space 3d hand pose estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 8969–8978 (2023) 4, 22 18 R. Jing et al

    2023

  20. [20]

    In: Proceedings of the European conference on computer vision (ECCV)

    Iqbal, U., Molchanov, P., Gall, T.B.J., Kautz, J.: Hand pose estimation via latent 2.5 d heatmap regression. In: Proceedings of the European conference on computer vision (ECCV). pp. 118–134 (2018) 3, 4

    2018

  21. [21]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Jiang, H., Liu, S., Wang, J., Wang, X.: Hand-object contact consistency reason- ing for human grasps generation. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 11107–11116 (2021) 3

    2021

  22. [22]

    2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp

    Jiang, Z., Rahmani, H., Black, S., Williams, B.M.: A probabilistic attention model withocclusion-awaretextureregressionfor3dhandreconstructionfromasinglergb image. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 758–768 (2023) 12

    2023

  23. [23]

    ArXivabs/2007.11858(2020) 10

    Jin, S., Xu, L., Xu, J., Wang, C., Liu, W., Qian, C., Ouyang, W., Luo, P.: Whole- body human pose estimation in the wild. ArXivabs/2007.11858(2020) 10

    arXiv 2007

  24. [24]

    A tutorial on chirp spread spectrum modulation for LoRaW AN: Basics and key advances,

    Kamdjou, H.M., Baudry, D., Havard, V., Ouchani, S.: Resource-constrained ex- tended reality operated with digital twin in industrial internet of things. IEEE Open J. Commun. Soc.5, 928–950 (2024).https://doi.org/10.1109/OJCOMS. 2024.33565081

    work page doi:10.1109/ojcoms 2024

  25. [25]

    IEEE Access13, 135609–135633 (2025).https:// doi.org/10.1109/ACCESS.2025.35900731

    Karim, M., Khalid, S., Lee, S., Almutairi, S.S., Namoun, A., Abohashrh, M.: Next generation human action recognition: A comprehensive review of state-of-the-art signal processing techniques. IEEE Access13, 135609–135633 (2025).https:// doi.org/10.1109/ACCESS.2025.35900731

    work page doi:10.1109/access.2025.35900731 2025

  26. [26]

    In: Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition

    Kim,J.,Gwon,M.G.,Park,H.,Kwon,H.,Um,G.M.,Kim,W.:Samplingismatter: Point-guided 3d human mesh reconstruction. In: Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition. pp. 12880–12889 (2023) 4

    2023

  27. [27]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Kulon, D., Guler, R.A., Kokkinos, I., Bronstein, M.M., Zafeiriou, S.: Weakly- supervised mesh-convolutional hand reconstruction in the wild. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 4990–5000 (2020) 4

    2020

  28. [28]

    arXiv preprint arXiv:2405.07167 (2024) 2, 4

    Li, H., Chen, P.P., Zhou, Y.: 3d hand mesh recovery from monocular rgb in camera space. arXiv preprint arXiv:2405.07167 (2024) 2, 4

    arXiv 2024

  29. [29]

    2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp

    Li, K., Yang, L., Zhan, X., Lv, J., Xu, W., Li, J., Lu, C.: Artiboost: Boosting artic- ulated 3d hand-object pose estimation via online exploration and synthesis. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 2740–2750 (2021) 12

    2022

  30. [30]

    IEEE Transactions on Image Processing33, 3964–3976 (2024) 5

    Li, Z., Wang, X., Liu, X., Jiang, J.: Binsformer: Revisiting adaptive bins for monoc- ular depth estimation. IEEE Transactions on Image Processing33, 3964–3976 (2024) 5

    2024

  31. [31]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 1954–1963 (2021) 4, 12

    1954

  32. [32]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Lin, K., Wang, L., Liu, Z.: Mesh graphormer. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 12939–12948 (2021) 4

    2021

  33. [33]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Liu, S., Jiang, H., Xu, J., Liu, S., Wang, X.: Semi-supervised 3d hand-object poses estimation with interactions in time. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 14687–14697 (2021) 3

    2021

  34. [34]

    ArXivabs/2303.05499(2023) 8, 10

    Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J., yue Li, C., Yang, J., Su, H., Zhu, J.J., Zhang, L.: Grounding dino: Marrying dino with grounded pre-training for open-set object detection. ArXivabs/2303.05499(2023) 8, 10

    Pith/arXiv arXiv 2023

  35. [35]

    IEEE Transactions on Multimedia26, 6822–6833 (2024) 12 ScaleHP 19

    Lu, H., Gou, S., Li, R.: Spmhand: Segmentation-guided progressive multi-path 3d hand pose and shape estimation. IEEE Transactions on Multimedia26, 6822–6833 (2024) 12 ScaleHP 19

    2024

  36. [36]

    Heredity 89, 403–403 (2002) 2, 6

    Manning, J.T.: Digit ratio: A pointer to fertility, behavior, and health. Heredity 89, 403–403 (2002) 2, 6

    2002

  37. [37]

    In: European Con- ference on Computer Vision

    Moon, G., Lee, K.M.: I2l-meshnet: Image-to-lixel prediction network for accurate 3d human pose and mesh estimation from a single rgb image. In: European Con- ference on Computer Vision. pp. 752–768. Springer (2020) 2, 3, 4, 12

    2020

  38. [38]

    6m: A dataset and baseline for 3d interacting hand pose estimation from a single rgb image

    Moon, G., Yu, S.I., Wen, H., Shiratori, T., Lee, K.M.: Interhand2. 6m: A dataset and baseline for 3d interacting hand pose estimation from a single rgb image. In: European Conference on Computer Vision. pp. 548–564. Springer (2020) 3

    2020

  39. [39]

    ACM Trans

    Nostadt, N., Abbink, D.A., Christ, O., Beckerle, P.: Embodiment, presence, and their intersections: Teleoperation and beyond. ACM Trans. Hum. Robot Interact. 9(4), 28:1–28:19 (2020).https://doi.org/10.1145/33892101

    work page doi:10.1145/33892101 2020

  40. [40]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Park, J., Oh, Y., Moon, G., Choi, H., Lee, K.M.: Handoccnet: Occlusion-robust 3d hand mesh estimation network. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 1496–1505 (2022) 4, 12

    2022

  41. [41]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Pavlakos, G., Shan, D., Radosavovic, I., Kanazawa, A., Fouhey, D., Malik, J.: Reconstructing hands in 3d with transformers. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 9826–9836 (2024) 4, 22, 23

    2024

  42. [42]

    2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp

    Pavlakos, G., Shan, D., Radosavovic, I., Kanazawa, A., Fouhey, D.F., Malik, J.: Reconstructing hands in 3d with transformers. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 9826–9836 (2023) 10

    2024

  43. [43]

    2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp

    Potamias, R.A., Zhang, J., Deng, J., Zafeiriou, S.: Wilor: End-to-end 3d hand local- ization and reconstruction in-the-wild. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 12242–12254 (2024) 6

    2025

  44. [44]

    Legal medicine10 4, 185–9 (2008) 2, 6

    Rastogi, P., Nagesh, K.R., Yoganarasimha, K.: Estimation of stature from hand dimensions of north and south indians. Legal medicine10 4, 185–9 (2008) 2, 6

    2008

  45. [45]

    Ren, K., Hu, L., Zhang, Z., Ye, Y., Xia, S.: Learning transformation-isomorphic latent space for accurate hand pose estimation (2025) 12

    2025

  46. [46]

    ACM Transactions on Graphics (TOG)36, 1 – 17 (2017) 22

    Romero, J., Tzionas, D., Black, M.J.: Embodied hands. ACM Transactions on Graphics (TOG)36, 1 – 17 (2017) 22

    2017

  47. [47]

    ACM Transactions on Graphics (TOG)36(6), 1–17 (2017) 3

    Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. ACM Transactions on Graphics (TOG)36(6), 1–17 (2017) 3

    2017

  48. [48]

    Saleem, M.U., Pinyoanuntapong, E., Patel, M.J., Xue, H., Helmy, A., Das, S., Wang, P.: Maskhand: Generative masked modeling for robust hand mesh recon- struction in the wild (2024) 12

    2024

  49. [49]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Shi, D., Wei, X., Li, L., Ren, Y., Tan, W.: End-to-end multi-person pose estima- tion with transformers. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 11069–11078 (2022) 4

    2022

  50. [50]

    In: European Conference on Computer Vision

    Spurr, A., Iqbal, U., Molchanov, P., Hilliges, O., Kautz, J.: Weakly supervised 3d hand pose estimation via biomechanical constraints. In: European Conference on Computer Vision. Springer (2020) 4

    2020

  51. [51]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Sun, Q., Wang, Y., Zeng, A., Yin, W., Wei, C., Wang, W., Mei, H., Leung, C.S., Liu, Z., Yang, L., et al.: Aios: All-in-one-stage expressive human pose and shape estimation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 1834–1843 (2024) 4

    2024

  52. [52]

    Frontiers Robotics AI7, 14 (2020).https://doi.org/10

    Toet,A.,Kuling,I.A.,Krom,B.N.,vanErp,J.B.F.:Towardenhancedteleoperation through embodiment. Frontiers Robotics AI7, 14 (2020).https://doi.org/10. 3389/FROBT.2020.000141 20 R. Jing et al

    arXiv 2020

  53. [53]

    In: European Conference on Computer Vision

    Valassakis, E., Garcia-Hernando, G.: Handdgp: Camera-space hand mesh predic- tion with differentiable global positioning. In: European Conference on Computer Vision. pp. 479–496. Springer (2024) 4, 12

    2024

  54. [54]

    The Journal of Medical Research (2015) 2, 6

    Varu, P., Manvar, P.J., Mangal, H.M., Kyada, H.C., Vadgama, D.K., Bhuva, S.D.: Determination of stature from hand dimensions. The Journal of Medical Research (2015) 2, 6

    2015

  55. [55]

    arXiv preprint arXiv:2511.13282 (2025) 2, 4

    Wang, K., Zheng, K., Shi, Y., Guo, C., Wu, J.: Towards metric-aware multi-person mesh recovery by jointly optimizing human crowd in camera space. arXiv preprint arXiv:2511.13282 (2025) 2, 4

    arXiv 2025

  56. [56]

    arXiv preprint arXiv:2507.02546 (2025) 5

    Wang, R., Xu, S., Dong, Y., Deng, Y., Xiang, J., Lv, Z., Sun, G., Tong, X., Yang, J.: Moge-2: Accurate monocular geometry with metric scale and sharp details. arXiv preprint arXiv:2507.02546 (2025) 5

    Pith/arXiv arXiv 2025

  57. [57]

    2023 IEEE International Conference on Multimedia and Expo (ICME) pp

    Wang, S., Wang, S., Yang, D., Li, M., Qian, Z., Su, L., Zhang, L.: Handgcat: Occlusion-robust 3d hand mesh reconstruction from monocular images. 2023 IEEE International Conference on Multimedia and Expo (ICME) pp. 2495–2500 (2023) 12

    2023

  58. [58]

    IEEE Transactions on Circuits and Systems for Video Technology29, 3258–3268 (2019) 10

    Wang, Y., Peng, C., Liu, Y.: Mask-pose cascaded cnn for 2d hand pose estimation from single color image. IEEE Transactions on Circuits and Systems for Video Technology29, 3258–3268 (2019) 10

    2019

  59. [59]

    2023 IEEE/CVF Con- ference on Computer Vision and Pattern Recognition (CVPR) pp

    Xu, H., Wang, T., Tang, X., Fu, C.W.: H2onet: Hand-occlusion-and-orientation- aware network for real-time 3d hand mesh reconstruction. 2023 IEEE/CVF Con- ference on Computer Vision and Pattern Recognition (CVPR) pp. 17048–17058 (2023) 12

    2023

  60. [60]

    arXiv preprint arXiv:2302.01593 (2023) 4

    Yang, J., Zeng, A., Liu, S., Li, F., Zhang, R., Zhang, L.: Explicit box detection unifies end-to-end multi-person pose estimation. arXiv preprint arXiv:2302.01593 (2023) 4

    arXiv 2023

  61. [61]

    2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) pp

    Yang, L., Li, B., Yang, G., Chang, Y., Liu, Z., Jiang, B., Xiao, J.: Deep neural network based visual inspection with 3d metric measurement of concrete defects using wall-climbing robot. 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) pp. 2849–2854 (2019) 2

    2019

  62. [62]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Yang, L., Chen, S., Yao, A.: Semihand: Semi-supervised hand pose estimation with consistency. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 11364–11373 (2021)

    2021

  63. [63]

    arXiv preprint arXiv:2008.05079 (2020) 3

    Yang, L., Li, J., Xu, W., Diao, Y., Lu, C.: Bihand: Recovering hand mesh with multi-stage bisected hourglass networks. arXiv preprint arXiv:2008.05079 (2020) 3

    arXiv 2008

  64. [64]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Yang, L., Zhan, X., Li, K., Xu, W., Li, J., Lu, C.: Cpf: Learning a contact poten- tial field to model the hand-object interaction. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 11097–11106 (2021) 3

    2021

  65. [65]

    In: Proceed- ings of the IEEE/CVF international conference on computer vision

    Yin, W., Zhang, C., Chen, H., Cai, Z., Yu, G., Wang, K., Chen, X., Shen, C.: Metric3d: Towards zero-shot metric 3d prediction from a single image. In: Proceed- ings of the IEEE/CVF international conference on computer vision. pp. 9043–9053 (2023) 5

    2023

  66. [66]

    In: Pro- ceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Yoshiyasu, Y.: Deformable mesh transformer for 3d human mesh recovery. In: Pro- ceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 17006–17015 (2023) 4, 12

    2023

  67. [67]

    Zhang, B., Wang, Y., Deng, X., Zhang, Y., Tan, P., Ma, C., Wang, H.: Interacting two-hand3dposeandshapereconstructionfromsinglecolorimage.In:Proceedings of the IEEE/CVF international conference on computer vision. pp. 11354–11363 (2021) 3 ScaleHP 21

    2021

  68. [68]

    In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023

    Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., Shum, H.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net (2023) 4

    2023

  69. [69]

    arXiv e-prints pp

    Zhang, H., Song, C., Zhang, H., Yu, T.: Metrichmr: Metric human mesh recovery from monocular images. arXiv e-prints pp. arXiv–2506 (2025) 5

    2025

  70. [70]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Zhang, X., Huang, H., Tan, J., Xu, H., Yang, C., Peng, G., Wang, L., Liu, J.: Hand image understanding via deep multi-task learning. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 11281–11292 (2021) 3

    2021

  71. [71]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Zhang, X., Li, Q., Mo, H., Zhang, W., Zheng, W.: End-to-end hand mesh recov- ery from a monocular rgb image. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 2354–2364 (2019) 3

    2019

  72. [72]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Zhao, Z., Zhao, X., Wang, Y.: Travelnet: Self-supervised physically plausible hand motion learning from monocular color images. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 11666–11676 (2021) 3

    2021

  73. [73]

    IEEE Robotics and Automation Letters5, 1540–1547 (2020) 2

    Zhong, F., Wang, Z., Chen, W., He, K., Wang, Y., hui Liu, Y.: Hand-eye calibration of surgical instrument for robotic surgery using interactive manipulation. IEEE Robotics and Automation Letters5, 1540–1547 (2020) 2

    2020

  74. [74]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Zhou, Y., Habermann, M., Xu, W., Habibie, I., Theobalt, C., Xu, F.: Monocular real-time hand shape and motion capture using multi-modal data. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 5346–5355 (2020)

    2020

  75. [75]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Zhou, Z., Zhou, S., Lv, Z., Zou, M., Tang, Y., Liang, J.: A simple baseline for efficient hand mesh reconstruction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 1367–1376 (2024) 12

    2024

  76. [76]

    In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021

    Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net (2021),https://openreview.net/forum?id=gZ9hCDWe6ke8

    2021

  77. [77]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Zimmermann, C., Ceylan, D., Yang, J., Russell, B., Argus, M., Brox, T.: Freihand: A dataset for markerless capture of hand pose and shape from single rgb images. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 813–822 (2019) 10, 12, 22 22 R. Jing et al. Supplementary Material S1 Evaluation Dataset Description We evaluate t...

    2019